Journal publications and preprints

Binned spectral power loss for improved prediction of chaotic systems

Journal of Computational Physics

Multimodal atmospheric super-resolution with deep generative models

Machine Learning: Earth

Differentiable turbulence: Closure as a partial differential equation constrained optimization

Physical Review Fluids

Divide and conquer: Learning chaotic dynamical systems with multistep penalty neural ordinary differential equations

Computer Methods in Applied Mechanics and Engineering

Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systems

arXiv:2603.12635

High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator

arXiv:2602.13416

SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs

arXiv:2602.02830

A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series

arXiv:2511.06609

MoWE: A Mixture of Weather Experts

arXiv:2509.09052

A note on the error analysis of data-driven closure models for large eddy simulations of turbulence

arXiv:2405.17612

Improved deep learning of chaotic dynamical systems with multistep penalty losses

arXiv:2410.05572

Computing Anti-Derivatives using Deep Neural Networks

arXiv:2209.09084